Engineering the AI applications (Part 6): nonlinear optimization
In this short post, I would like to share a few lessons that we have learnt while developing the AI applications.
While designing AI/ML solutions, we often encounter solving "local and global optimization" problems. There are numerous resources out there! However, we have chosen the following resources (libraries) to be built into our Edge AI platform.
NLopt: a free/open-source library for nonlinear optimization
NLopt provides a common interface for a number of different free optimization routines available online as well as original implementations of various other algorithms.
How does a common interface of NLopt help?
While implementing AI solutions, it is often required to compare the optimization algorithms to meet certain objectives. Without a common interface, it is tedious to switch algorithms.
NLOpt comes handy. It can be built for Android ARM64 as well.
Affiliations
I write posts for Vidcentum Technologies where I am founder director. Some of the articles are published in my blogs / articles / posts as well as on the company timeline / posts.